Explore the Dataset

Demographics: Population, Race, Gender Data County

This dataset provides a detailed breakdown of demographic information for counties across the United States, derived from the U.S. Census Bureau’s 2023 American Community Survey (ACS). The data includes population counts by gender, race, and ethnicity, alongside unique identifiers for each county using State and County FIPS codes.

Dataset Features:

• County: Name of the county.
• State: Name of the state the county belongs to.
• State FIPS Code: Federal Information Processing Standard (FIPS) code for the state.
• County FIPS Code: FIPS code for the county.
• FIPS: Combined State and County FIPS codes, a unique identifier for each county.
• Total Population: Total population in the county.
• Male Population: Number of males in the county.
• Female Population: Number of females in the county.
• Total Race Responses: Total race-related responses recorded in the survey.
• White Alone: Number of individuals identifying as White alone.
• Black or African American Alone: Number of individuals identifying as Black or African American alone.
• Hispanic or Latino: Number of individuals identifying as Hispanic or Latino.

# Imports

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.graph_objects as go
import plotly.express as px
import folium
import requests
from branca.colormap import LinearColormap

df = pd.read_csv('demographics_data/demographic_data.csv')
df

	County	State	State FIPS Code	County FIPS Code	FIPS	Total Population	Male Population	Female Population	Total Race Responses	White Alone	Black or African American Alone	Hispanic or Latino
0	Autauga County	Alabama	1	1	1001	59285	28669	30616	59285	43616	11829	2188
1	Baldwin County	Alabama	1	3	1003	239945	117316	122629	239945	198721	19144	13393
2	Barbour County	Alabama	1	5	1005	24757	12906	11851	24757	10891	11616	1490
3	Bibb County	Alabama	1	7	1007	22152	11824	10328	22152	16634	4587	744
4	Blount County	Alabama	1	9	1009	59292	29934	29358	59292	53062	747	5962
...	...	...	...	...	...	...	...	...	...	...	...	...
3217	Vega Baja Municipio	Puerto Rico	72	145	72145	54058	25765	28293	54058	13681	2249	53036
3218	Vieques Municipio	Puerto Rico	72	147	72147	8147	4178	3969	8147	1028	222	7803
3219	Villalba Municipio	Puerto Rico	72	149	72149	21778	10510	11268	21778	7552	2219	21700
3220	Yabucoa Municipio	Puerto Rico	72	151	72151	29868	14381	15487	29868	2001	5900	29732
3221	Yauco Municipio	Puerto Rico	72	153	72153	33509	15920	17589	33509	24597	649	33243

3222 rows × 12 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3222 entries, 0 to 3221
Data columns (total 12 columns):
 #   Column                           Non-Null Count  Dtype 
---  ------                           --------------  ----- 
 0   County                           3222 non-null   object
 1   State                            3222 non-null   object
 2   State FIPS Code                  3222 non-null   int64 
 3   County FIPS Code                 3222 non-null   int64 
 4   FIPS                             3222 non-null   int64 
 5   Total Population                 3222 non-null   int64 
 6   Male Population                  3222 non-null   int64 
 7   Female Population                3222 non-null   int64 
 8   Total Race Responses             3222 non-null   int64 
 9   White Alone                      3222 non-null   int64 
 10  Black or African American Alone  3222 non-null   int64 
 11  Hispanic or Latino               3222 non-null   int64 
dtypes: int64(10), object(2)
memory usage: 302.2+ KB

df.isnull().sum()

County                             0
State                              0
State FIPS Code                    0
County FIPS Code                   0
FIPS                               0
Total Population                   0
Male Population                    0
Female Population                  0
Total Race Responses               0
White Alone                        0
Black or African American Alone    0
Hispanic or Latino                 0
dtype: int64

df_state = df.groupby('State').agg({
    'State FIPS Code':'first',
    'County FIPS Code':'first',
    'Total Population':'sum',
    'Male Population':'sum',
    'Female Population':'sum',
    'White Alone':'sum',
    'Black or African American Alone':'sum',
    'Hispanic or Latino':'sum'}).reset_index()

df_state

	State	State FIPS Code	County FIPS Code	Total Population	Male Population	Female Population	White Alone	Black or African American Alone	Hispanic or Latino
0	Alabama	1	1	5054253	2453419	2600834	3303370	1318507	271640
1	Alaska	2	13	733971	385319	348652	445545	22774	52473
2	Arizona	4	1	7268175	3628694	3639481	4593653	336931	2255770
3	Arkansas	5	1	3032651	1495958	1536693	2148886	452127	265833
4	California	6	1	39242785	19605882	19636903	17248779	2173343	15630830
5	Colorado	8	1	5810774	2942568	2868206	4268784	232985	1291078
6	Connecticut	9	110	3598348	1765117	1833231	2431342	384753	640668
7	Delaware	10	1	1005872	487585	518287	621799	220645	107829
8	District of Columbia	11	1	672079	320001	352078	262549	290772	77760
9	Florida	12	1	21928881	10773620	11155261	13136701	3363769	5865737
10	Georgia	13	1	10822590	5281762	5540828	5677531	3391689	1158299
11	Hawaii	15	1	1445635	727473	718162	325356	27740	142225
12	Idaho	16	1	1893296	952080	941216	1578020	14108	252466
13	Illinois	17	1	12692653	6270399	6422254	8038512	1750414	2348118
14	Indiana	18	1	6811752	3377011	3434741	5347678	630680	569410
15	Iowa	19	1	3195937	1601453	1594484	2735263	123234	223471
16	Kansas	20	1	2937569	1473655	1463914	2289052	159829	389514
17	Kentucky	21	1	4510725	2233870	2276855	3774581	355237	212163
18	Louisiana	22	1	4621025	2262822	2358203	2678942	1434953	321022
19	Maine	23	1	1377400	678363	699037	1258122	23145	28609
20	Maryland	24	1	6170738	3002079	3168659	3060731	1825880	744272
21	Massachusetts	25	1	6992395	3416765	3575630	4945674	489390	904679
22	Michigan	26	1	10051595	4982079	5069516	7516312	1346689	576808
23	Minnesota	27	1	5713716	2862134	2851582	4476710	388789	353608
24	Mississippi	28	1	2951438	1431521	1519917	1661873	1090777	106126
25	Missouri	29	1	6168181	3040690	3127491	4831646	686616	311924
26	Montana	30	1	1105072	560035	545037	946776	6015	48519
27	Nebraska	31	1	1965926	987506	978420	1570391	93595	242226
28	Nevada	32	1	3141000	1582476	1558524	1670302	295802	917057
29	New Hampshire	33	1	1387834	692568	695266	1234149	21164	62758
30	New Jersey	34	1	9267014	4558671	4708343	5276142	1201053	2032968
31	New Mexico	35	1	2114768	1050368	1064400	1133871	44709	1018321
32	New York	36	1	19872319	9702417	10169902	11340944	2927008	3898652
33	North Carolina	37	1	10584340	5177887	5406453	6695587	2178329	1158750
34	North Dakota	38	1	779361	399126	380235	653820	25209	34963
35	Ohio	39	1	11780046	5809077	5970969	9167192	1446466	537559
36	Oklahoma	40	1	3995260	1988686	2006574	2668453	282536	490797
37	Oregon	41	1	4238714	2113849	2124865	3247656	81642	605467
38	Pennsylvania	42	1	12986518	6400912	6585606	9844085	1393616	1087732
39	Puerto Rico	72	1	3254885	1540987	1713898	1146311	237762	3215824
40	Rhode Island	44	1	1095371	537173	558198	792361	63862	187503
41	South Carolina	45	1	5212774	2537456	2675318	3339447	1318630	368900
42	South Dakota	46	3	899194	455597	443597	733035	20149	41281
43	Tennessee	47	1	6986082	3428050	3558032	5133249	1108897	496457
44	Texas	48	1	29640343	14789987	14850356	15984990	3626137	11697134
45	Utah	49	1	3331187	1686562	1644625	2688129	37772	513013
46	Vermont	50	1	645254	320321	324933	589835	7887	16058
47	Virginia	51	1	8657499	4278490	4379009	5344175	1623031	929140
48	Washington	53	1	7740984	3898212	3842772	5251386	306214	1089609
49	West Virginia	54	1	1784462	890156	894306	1622009	58519	36125
50	Wisconsin	55	1	5892023	2950540	2941483	4791680	361890	457687
51	Wyoming	56	1	579761	296646	283115	498371	4982	60581

df_state.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 52 entries, 0 to 51
Data columns (total 9 columns):
 #   Column                           Non-Null Count  Dtype 
---  ------                           --------------  ----- 
 0   State                            52 non-null     object
 1   State FIPS Code                  52 non-null     int64 
 2   County FIPS Code                 52 non-null     int64 
 3   Total Population                 52 non-null     int64 
 4   Male Population                  52 non-null     int64 
 5   Female Population                52 non-null     int64 
 6   White Alone                      52 non-null     int64 
 7   Black or African American Alone  52 non-null     int64 
 8   Hispanic or Latino               52 non-null     int64 
dtypes: int64(8), object(1)
memory usage: 3.8+ KB

Population

Total Population

By State

# Map state names to abbreviations
state_abbr = {
    "Alabama": "AL", "Alaska": "AK", "Arizona": "AZ", "Arkansas": "AR",
    "California": "CA", "Colorado": "CO", "Connecticut": "CT", "Delaware": "DE",
    "Florida": "FL", "Georgia": "GA", "Hawaii": "HI", "Idaho": "ID", "Illinois": "IL",
    "Indiana": "IN", "Iowa": "IA", "Kansas": "KS", "Kentucky": "KY", "Louisiana": "LA",
    "Maine": "ME", "Maryland": "MD", "Massachusetts": "MA", "Michigan": "MI",
    "Minnesota": "MN", "Mississippi": "MS", "Missouri": "MO", "Montana": "MT",
    "Nebraska": "NE", "Nevada": "NV", "New Hampshire": "NH", "New Jersey": "NJ",
    "New Mexico": "NM", "New York": "NY", "North Carolina": "NC", "North Dakota": "ND",
    "Ohio": "OH", "Oklahoma": "OK", "Oregon": "OR", "Pennsylvania": "PA",
    "Rhode Island": "RI", "South Carolina": "SC", "South Dakota": "SD",
    "Tennessee": "TN", "Texas": "TX", "Utah": "UT", "Vermont": "VT",
    "Virginia": "VA", "Washington": "WA", "West Virginia": "WV", "Wisconsin": "WI",
    "Wyoming": "WY"
}

df_state['State Abbreviation'] = df_state['State'].map(state_abbr)

df_state.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 52 entries, 0 to 51
Data columns (total 10 columns):
 #   Column                           Non-Null Count  Dtype 
---  ------                           --------------  ----- 
 0   State                            52 non-null     object
 1   State FIPS Code                  52 non-null     int64 
 2   County FIPS Code                 52 non-null     int64 
 3   Total Population                 52 non-null     int64 
 4   Male Population                  52 non-null     int64 
 5   Female Population                52 non-null     int64 
 6   White Alone                      52 non-null     int64 
 7   Black or African American Alone  52 non-null     int64 
 8   Hispanic or Latino               52 non-null     int64 
 9   State Abbreviation               50 non-null     object
dtypes: int64(8), object(2)
memory usage: 4.2+ KB

formatted_columns = [
    'Total Population', 'Male Population', 'Female Population', 
    'White Alone', 'Black or African American Alone', 'Hispanic or Latino'
]

# Exclude 'Total Population' from the percentage calculations
percentage_columns = [col for col in formatted_columns if col != 'Total Population']

# Calculate the percentage values based on Total Population
percentage_values = df_state[percentage_columns]\
    .div(df_state['Total Population'], axis=0)\
    .mul(100)\
    .round(2)

# Rename the percentage columns to include a '%' suffix in the header
percentage_values.columns = percentage_values.columns + " (%)"

# Convert the percentage values to strings with an appended "%" sign
formatted_percentage_values = percentage_values.astype(str) + '%'

# Combine the original (unformatted) numeric columns with the formatted percentage columns
df_state = pd.concat(
    [df_state[['State', 'State Abbreviation'] + formatted_columns], formatted_percentage_values],
    axis=1)

df_state.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 52 entries, 0 to 51
Data columns (total 13 columns):
 #   Column                               Non-Null Count  Dtype 
---  ------                               --------------  ----- 
 0   State                                52 non-null     object
 1   State Abbreviation                   50 non-null     object
 2   Total Population                     52 non-null     int64 
 3   Male Population                      52 non-null     int64 
 4   Female Population                    52 non-null     int64 
 5   White Alone                          52 non-null     int64 
 6   Black or African American Alone      52 non-null     int64 
 7   Hispanic or Latino                   52 non-null     int64 
 8   Male Population (%)                  52 non-null     object
 9   Female Population (%)                52 non-null     object
 10  White Alone (%)                      52 non-null     object
 11  Black or African American Alone (%)  52 non-null     object
 12  Hispanic or Latino (%)               52 non-null     object
dtypes: int64(6), object(7)
memory usage: 5.4+ KB

df_state.head()

	State	State Abbreviation	Total Population	Male Population	Female Population	White Alone	Black or African American Alone	Hispanic or Latino	Male Population (%)	Female Population (%)	White Alone (%)	Black or African American Alone (%)	Hispanic or Latino (%)
0	Alabama	AL	5054253	2453419	2600834	3303370	1318507	271640	48.54%	51.46%	65.36%	26.09%	5.37%
1	Alaska	AK	733971	385319	348652	445545	22774	52473	52.5%	47.5%	60.7%	3.1%	7.15%
2	Arizona	AZ	7268175	3628694	3639481	4593653	336931	2255770	49.93%	50.07%	63.2%	4.64%	31.04%
3	Arkansas	AR	3032651	1495958	1536693	2148886	452127	265833	49.33%	50.67%	70.86%	14.91%	8.77%
4	California	CA	39242785	19605882	19636903	17248779	2173343	15630830	49.96%	50.04%	43.95%	5.54%	39.83%

tooltip = {
        'State': True,
        'Total Population': True,
        'Male Population (%)': True,
        'Female Population (%)': True,
        'White Alone (%)': True,
        'Black or African American Alone (%)': True,
        'Hispanic or Latino (%)': True,
    }

label_data = {
        'State': 'State',
        'Total Population': 'Population',
        'Male Population (%)': 'Male Population (%)',
        'Female Population (%)': 'Female Population (%)',
        'White Alone (%)': 'White Alone (%)',
        'Black or African American Alone (%)': 'Black or African American Alone (%)',
        'Hispanic or Latino (%)': 'Hispanic or Latino (%)'
}

# Create the heatmap
fig = px.choropleth(
    df_state,
    locations='State Abbreviation',  # Using abbreviations for location mapping
    locationmode='USA-states',
    color='Total Population',
    scope='usa',
    title='Heat Map of Total Population by State',
    color_continuous_scale='icefire',
    hover_data= tooltip,
    labels= label_data
)
fig.write_html("chloropleth_map.html")
fig.show()

Unable to display output for mime type(s): application/vnd.plotly.v1+json

By County

# Load the counties GeoJSON file
geojson_url = "https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json"
geojson_data = requests.get(geojson_url).json()

# Ensure FIPS codes are strings with 5 digits
df["FIPS"] = df["FIPS"].astype(str).str.zfill(5)

# Create a mapping of FIPS to Total Population
population_dict = df.set_index("FIPS")["Total Population"].to_dict()

# Add Total Population to GeoJSON properties
for feature in geojson_data["features"]:
    fips = feature["id"]
    if fips in population_dict:
        feature["properties"]["Total Population"] = population_dict[fips]
    else:
        feature["properties"]["Total Population"] = None

# Normalize population for color mapping
min_pop, max_pop = df["Total Population"].min(), df["Total Population"].max()
colormap = LinearColormap(colors=["blue", "white", "red"],
                             vmin=min_pop, vmax=max_pop)

# Create a Folium map centered in the US
m = folium.Map(location=[37.8, -96], zoom_start=4, tiles="cartodb positron")

# Add the choropleth layer without built-in fill_color
choropleth = folium.Choropleth(
    geo_data=geojson_data,
    name="choropleth",
    data=df,
    columns=["FIPS", "Total Population"],
    key_on="feature.id",
    fill_color=None,  # Disable built-in color scale
    fill_opacity=0.7,
    line_opacity=0.2,
    legend_name="Total Population by County"
).add_to(m)

# Apply the custom colormap
for feature in geojson_data["features"]:
    fips = feature["id"]
    county_data = df[df["FIPS"] == fips]

    if not county_data.empty:
        pop = county_data["Total Population"].values[0]
        color = colormap(pop)
    else:
        color = "#D3D3D3"

    feature["properties"]["style"] = {"fillColor": color, "fillOpacity": 0.7, "color": "black", "weight": 0.2}

# Add tooltips with County Name & Population
tooltip = folium.features.GeoJsonTooltip(
    fields=["NAME", "Total Population"],
    aliases=["County:", "Population:"],
    localize=True,
    sticky=True,
    labels=True,
    style="background-color: white; color: black; font-size: 12px; padding: 5px;"
)

# Attach GeoJSON with tooltips and styles
folium.GeoJson(
    geojson_data,
    tooltip=tooltip,
    style_function=lambda feature: feature["properties"]["style"]
).add_to(m)

# Add the custom colormap to chloro map
colormap.caption = "Total Population by County"
m.add_child(colormap)

# Display the map
m

Make this Notebook Trusted to load map: File -> Trust Notebook

Total Gender Distribution

df_state.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 52 entries, 0 to 51
Data columns (total 13 columns):
 #   Column                               Non-Null Count  Dtype 
---  ------                               --------------  ----- 
 0   State                                52 non-null     object
 1   State Abbreviation                   50 non-null     object
 2   Total Population                     52 non-null     int64 
 3   Male Population                      52 non-null     int64 
 4   Female Population                    52 non-null     int64 
 5   White Alone                          52 non-null     int64 
 6   Black or African American Alone      52 non-null     int64 
 7   Hispanic or Latino                   52 non-null     int64 
 8   Male Population (%)                  52 non-null     object
 9   Female Population (%)                52 non-null     object
 10  White Alone (%)                      52 non-null     object
 11  Black or African American Alone (%)  52 non-null     object
 12  Hispanic or Latino (%)               52 non-null     object
dtypes: int64(6), object(7)
memory usage: 5.4+ KB

total_male_population = df_state['Male Population'].sum()
total_female_population = df_state['Female Population'].sum()

pie_data = {
    'Gender': ['Male', 'Female'],
    'Population': [total_male_population, total_female_population]
}

# Create the pie chart
fig = px.pie(
    pie_data,
    names='Gender',
    values='Population',
    title='Total Male Population vs Female Population (USA)',
    color='Gender',
    color_discrete_map={
        'Male': '#0b6380', # blue
        'Female': '#d18e3b' # orange
    }
)

fig.update_traces(textinfo='percent+label')

fig.show()

Unable to display output for mime type(s): application/vnd.plotly.v1+json

# Calculate the difference between female and male populations
df_state['Difference'] = df_state['Female Population'] - df_state['Male Population']

fig = px.choropleth(
    df_state,
    locations='State Abbreviation',  # using the state abbreviations for mapping
    locationmode='USA-states',
    scope='usa',
    # Make sure you have a column for 'Difference'. If not, compute it:
    # For example, if 'Difference' is not in df_states, you can calculate it as:
    # df_states['Difference'] = df_states['Female Population'] - df_states['Male Population']
    color='Difference',
    color_continuous_scale=px.colors.diverging.RdBu_r,
    labels={'Difference': 'Female - Male'},
    title='Choropleth Map of USA by Gender Population',
    hover_name='State',
    hover_data={'Difference': False},
    custom_data=['Female Population (%)', 'Male Population (%)']
)

# Add black borders to state boundaries
fig.update_traces(marker_line_color='black', marker_line_width=0.5)

# Update hovertemplate to display the percentages
fig.update_traces(
    hovertemplate=(
        'State: %{hovertext}<br>'
        'Female Percentage: %{customdata[0]}<br>'
        'Male Percentage: %{customdata[1]}<br>'
        'Difference: %{z:.2f}k<extra></extra>'
    )
)

# Update hovertext with state names
fig.for_each_trace(lambda t: t.update(hovertext=df_state['State']))

fig.show()

Unable to display output for mime type(s): application/vnd.plotly.v1+json

Race Distribution

sns.pairplot(df[["Total Population", "White Alone", "Black or African American Alone", "Hispanic or Latino"]])
plt.show()

# Scatter plot: Total Population vs. White Alone
plt.figure(figsize=(8,6))
sns.scatterplot(data=df, x="Total Population", y="White Alone", alpha=0.5)
plt.title("Total Population vs. White Alone")
plt.xlabel("Total Population")
plt.ylabel("White Alone Population")
plt.xscale("log")
plt.yscale("log")
plt.show()

# Total Population vs. Black or African American Alone
sns.scatterplot(data=df, x="Total Population", y="Black or African American Alone", alpha=0.5)
plt.title("Total Population vs. Black or African American Alone")
plt.xlabel("Total Population")
plt.ylabel("Black Population")
plt.xscale("log")
plt.yscale("log")
plt.show()

# Total Population vs. Hispanic or Latino
sns.scatterplot(data=df, x="Total Population", y="Hispanic or Latino", alpha=0.5)
plt.title("Total Population vs. Hispanic or Latino")
plt.xlabel("Total Population")
plt.ylabel("Black Population")
plt.xscale("log")
plt.yscale("log")
plt.show()

# Helper function to get race data for a state or county
def get_race_data(state=None, county=None):
    filtered_df = df
    if state:
        filtered_df = filtered_df[filtered_df['State'] == state]
    if county:
        filtered_df = filtered_df[filtered_df['County'] == county]

    race_totals = {
        'White Alone': filtered_df['White Alone'].sum(),
        'Black or African American Alone': filtered_df['Black or African American Alone'].sum(),
        'Hispanic or Latino': filtered_df['Hispanic or Latino'].sum(),
    }
    return list(race_totals.keys()), list(race_totals.values())

# Initialize the figure with data for the US
initial_labels, initial_values = get_race_data()
fig = go.Figure(data=[go.Pie(labels=initial_labels, values=initial_values, name="All States")])

# Create a mapping of states to their county dropdowns
state_to_county_buttons = {
    state: [
        dict(
            label="All Counties",
            method="update",
            args=[
                {"labels": [get_race_data(state)[0]], "values": [get_race_data(state)[1]]},
                {"title": f"Race per Population in {state} (All Counties)"}
            ]
        )
    ] + [
        dict(
            label=county,
            method="update",
            args=[
                {"labels": [get_race_data(state, county)[0]], "values": [get_race_data(state, county)[1]]},
                {"title": f"Race per Population in {county}, {state}"}
            ]
        )
        for county in df[df['State'] == state]['County'].unique()
    ]
    for state in df['State'].unique()
}

# State dropdown buttons
state_buttons = [
    dict(
        label="United States",
        method="update",
        args=[
            {"labels": [initial_labels], "values": [initial_values]},
            {"title": "Race per Population in the United States"}
        ]
    )
] + [
    dict(
        label=state,
        method="update",
        args=[
            {"labels": [state_to_county_buttons[state][0]['args'][0]['labels'][0]],  
             "values": [state_to_county_buttons[state][0]['args'][0]['values'][0]]},
            {"title": f"Race per Population in {state}"}
        ]
    )
    for state in df['State'].unique()
]

# Update layout with dropdowns
fig.update_layout(
    updatemenus=[
        dict(
            buttons=state_buttons,
            direction="down",
            showactive=True,
            x=0.2,
            xanchor="left",
            y=1.1,
            yanchor="top",
            pad={"r": 10, "t": 10},
            name="State",
        ),
        dict(
            buttons=state_to_county_buttons[df['State'].unique()[0]],  # Default to the first state's counties
            direction="down",
            showactive=True,
            x=0.6,
            xanchor="left",
            y=1.1,
            yanchor="top",
            pad={"r": 10, "t": 10},
            name="County",
        ),
    ],
    title="Race per Population in the United States",
    title_x=0.27,
)

fig.show()

Unable to display output for mime type(s): application/vnd.plotly.v1+json